Leveraging Large Language Models for Information Verification -- an Engineering Approach
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908416743571456 |
|---|---|
| author | Hung, Nguyen Nang Trong, Nguyen Thanh Toan, Vuong Thanh Phuoc, Nguyen An Tu, Dao Minh Tuan, Nguyen Manh Duc Mau, Nguyen Dinh |
| author_facet | Hung, Nguyen Nang Trong, Nguyen Thanh Toan, Vuong Thanh Phuoc, Nguyen An Tu, Dao Minh Tuan, Nguyen Manh Duc Mau, Nguyen Dinh |
| contents | For the ACMMM25 challenge, we present a practical engineering approach to multimedia news source verification, utilizing Large Language Models (LLMs) like GPT-4o as the backbone of our pipeline. Our method processes images and videos through a streamlined sequence of steps: First, we generate metadata using general-purpose queries via Google tools, capturing relevant content and links. Multimedia data is then segmented, cleaned, and converted into frames, from which we select the top-K most informative frames. These frames are cross-referenced with metadata to identify consensus or discrepancies. Additionally, audio transcripts are extracted for further verification. Noticeably, the entire pipeline is automated using GPT-4o through prompt engineering, with human intervention limited to final validation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18274 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models for Information Verification -- an Engineering Approach Hung, Nguyen Nang Trong, Nguyen Thanh Toan, Vuong Thanh Phuoc, Nguyen An Tu, Dao Minh Tuan, Nguyen Manh Duc Mau, Nguyen Dinh Machine Learning For the ACMMM25 challenge, we present a practical engineering approach to multimedia news source verification, utilizing Large Language Models (LLMs) like GPT-4o as the backbone of our pipeline. Our method processes images and videos through a streamlined sequence of steps: First, we generate metadata using general-purpose queries via Google tools, capturing relevant content and links. Multimedia data is then segmented, cleaned, and converted into frames, from which we select the top-K most informative frames. These frames are cross-referenced with metadata to identify consensus or discrepancies. Additionally, audio transcripts are extracted for further verification. Noticeably, the entire pipeline is automated using GPT-4o through prompt engineering, with human intervention limited to final validation. |
| title | Leveraging Large Language Models for Information Verification -- an Engineering Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.18274 |